Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Numerical Question Answering research benchmarks · SOTA2 Research

Numerical Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Human Expert Performance

91.16Execution Accuracy

33

Feb 27, 2026

FinLongDocQA 1.0 (test)

FinLongDocAgent

41.34EM

19

Apr 7, 2026

FinQA 1.0 (test)

Human Expert Performance

91.16Execution Accuracy

14

Feb 26, 2026

83Program Accuracy

6

Feb 27, 2026

Popular datasets

FinQA MathQA FinLongDocQA

Follow for updates

Join SOTA2 Contact